Triple
T7658598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ms. Perkins |
E173446
|
entity |
| Predicate | worksInUniverse |
P58964
|
FINISHED |
| Object | criminal underworld |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: criminal underworld | Statement: [Ms. Perkins, worksInUniverse, criminal underworld]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worksInUniverse Context triple: [Ms. Perkins, worksInUniverse, criminal underworld]
-
A.
hasFictionalUniverseElement
Indicates that one entity is a component, feature, or constituent part of the fictional universe represented by the other entity.
-
B.
portraysFictionalUniverse
Indicates that one entity depicts, represents, or presents the fictional universe in which another entity is set.
-
C.
fictionalUniverse
Indicates that two entities exist within, or are associated with, the same fictional universe or narrative setting.
-
D.
hasInUniverseRole
chosen
Indicates that an entity holds or performs a specific role or function within a particular fictional or defined universe.
-
E.
fandomScope
Indicates the extent or boundaries of a fandom-related relationship, such as how broadly or narrowly a fan’s interest, participation, or recognition applies.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69c69955517c819085bc715b96d304d2 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7061cbc3c8190a917dd7e71214182 |
completed | March 27, 2026, 10:35 p.m. |
| PD | Predicate disambiguation | batch_69c7015dd8fc8190bc5f52a12bd46209 |
completed | March 27, 2026, 10:14 p.m. |
Created at: March 27, 2026, 3:59 p.m.